COVID-19 Analysis
Katie Forthman
Fri May 15 09:52:11 2020
Click here for interactive plots:
Click here to see how cities and counties overlap:
Compare COVID stats to Neighborhood Factors
data.cor <- cor(county.Demo_and_Covid.allcounties[,-1], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
Compare COVID stats to 500 cities data and Neighborhood Factors
data.cor2 <- cor(county.Demo_and_Covid.500counties[,-c(1:2)], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor2, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
corrplot.mixed(data.cor2[7:13,c(1:5, 14:42,6)], upper = 'ellipse', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
—-Linear Mixed Effects Model —-
this.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)", data = county.Demo_and_Covid.500counties)## Warning: Some predictor variables are on very different scales: consider
## rescaling
## Warning: Some predictor variables are on very different scales: consider
## rescalingprint(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -1210.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.0038 -0.3160 -0.0761 0.1681 6.3638
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000001791 0.001338
## Residual 0.000012302 0.003507
## Number of obs: 178, groups: stateID, 33
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0120719910 0.0095625180 74.3706058559
## Affluence 0.0044865088 0.0010894740 112.0148336490
## Singletons.in.Tract 0.0007760572 0.0008806835 147.5713665474
## Seniors.in.Tract 0.0005272432 0.0011570409 154.0800380795
## African.Americans.in.Tract 0.0009235728 0.0009679062 155.2698928508
## Noncitizens.in.Tract 0.0009161526 0.0007510725 129.2794215818
## High.BP 0.0001879746 0.0001843099 119.0807510063
## Binge.Drinking 0.0001713715 0.0001573536 48.4803949152
## Cancer -0.0010770574 0.0010832921 110.4315146811
## Asthma 0.0007960025 0.0005592401 51.9302403898
## Heart.Disease 0.0015062938 0.0012874816 83.3013711538
## COPD -0.0002817254 0.0010712462 82.1147640089
## Smoking -0.0000483153 0.0002232153 88.7158291786
## Diabetes -0.0006457079 0.0005281133 89.0738184689
## No.Physical.Activity -0.0000425574 0.0002029702 97.9629023771
## Obesity 0.0002595430 0.0001735021 118.1707622825
## Poor.Sleeping.Habits -0.0000427521 0.0001613231 129.5755276669
## Poor.Mental.Health -0.0000795899 0.0004251413 34.6814614071
## Testing_Rate 0.0000006823 0.0000003028 43.8073527572
## Hospitalization_Rate -0.0000560787 0.0000881350 31.3646402187
## t value Pr(>|t|)
## (Intercept) -1.262 0.2107
## Affluence 4.118 0.0000734 ***
## Singletons.in.Tract 0.881 0.3796
## Seniors.in.Tract 0.456 0.6493
## African.Americans.in.Tract 0.954 0.3415
## Noncitizens.in.Tract 1.220 0.2248
## High.BP 1.020 0.3099
## Binge.Drinking 1.089 0.2815
## Cancer -0.994 0.3223
## Asthma 1.423 0.1606
## Heart.Disease 1.170 0.2454
## COPD -0.263 0.7932
## Smoking -0.216 0.8291
## Diabetes -1.223 0.2247
## No.Physical.Activity -0.210 0.8344
## Obesity 1.496 0.1373
## Poor.Sleeping.Habits -0.265 0.7914
## Poor.Mental.Health -0.187 0.8526
## Testing_Rate 2.254 0.0293 *
## Hospitalization_Rate -0.636 0.5292
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence 0.102
## Sngltns.n.T 0.028 0.069
## Snrs.n.Trct 0.545 0.384 0.195
## Afrcn.Am..T 0.145 0.153 -0.403 0.144
## Nnctzns.n.T -0.007 0.103 0.037 0.065 -0.085
## High.BP -0.024 0.245 0.056 0.106 -0.089 0.389
## Bing.Drnkng -0.307 -0.177 -0.295 -0.173 0.071 0.027 0.123
## Cancer -0.590 -0.181 0.180 -0.316 -0.070 -0.132 -0.361 -0.094
## Asthma -0.398 -0.189 -0.252 -0.207 0.089 0.096 0.172 0.003 0.067
## Heart.Dises -0.155 0.084 -0.299 -0.153 0.251 -0.105 -0.001 0.059 -0.469
## COPD 0.573 0.018 0.153 0.275 -0.024 0.273 0.152 0.087 -0.279
## Smoking -0.143 0.147 -0.173 -0.100 -0.048 0.014 -0.061 -0.298 0.078
## Diabetes 0.102 -0.354 -0.102 -0.219 -0.304 -0.312 -0.535 0.049 0.230
## N.Physcl.Ac -0.196 -0.027 0.080 -0.025 -0.032 -0.222 -0.085 0.116 0.471
## Obesity 0.003 0.415 0.434 0.304 0.135 0.189 -0.093 -0.226 0.106
## Pr.Slpng.Hb -0.445 -0.391 0.136 -0.358 -0.341 -0.032 -0.188 0.095 0.136
## Pr.Mntl.Hlt -0.354 0.269 -0.068 -0.049 0.097 -0.162 -0.051 0.084 0.330
## Testing_Rat 0.238 -0.100 0.013 0.033 0.023 -0.063 -0.045 -0.014 -0.205
## Hsptlztn_Rt -0.106 -0.243 -0.093 -0.219 -0.052 -0.088 -0.112 -0.121 0.018
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H Pr.M.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.280
## COPD -0.389 -0.563
## Smoking 0.080 0.203 -0.498
## Diabetes -0.134 -0.305 -0.071 0.226
## N.Physcl.Ac 0.024 -0.371 -0.020 -0.329 -0.089
## Obesity -0.267 -0.093 0.163 -0.199 -0.381 -0.061
## Pr.Slpng.Hb 0.076 0.252 -0.195 -0.025 -0.022 -0.105 -0.165
## Pr.Mntl.Hlt -0.217 0.090 -0.460 0.069 0.005 0.063 0.078 -0.169
## Testing_Rat -0.359 -0.053 0.230 0.139 0.147 -0.312 0.119 -0.140 -0.164
## Hsptlztn_Rt 0.071 0.086 -0.080 0.080 0.081 -0.064 -0.037 0.001 -0.104
## Tstn_R
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises
## COPD
## Smoking
## Diabetes
## N.Physcl.Ac
## Obesity
## Pr.Slpng.Hb
## Pr.Mntl.Hlt
## Testing_Rat
## Hsptlztn_Rt 0.213
## fit warnings:
## Some predictor variables are on very different scales: consider rescalingthis.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)", data = county.Demo_and_Covid.500counties)
print(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -2499.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6832 -0.3755 -0.0799 0.2225 7.1939
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000006876 0.002622
## Residual 0.000010381 0.003222
## Number of obs: 326, groups: stateID, 51
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) -0.02001587 0.00733872 197.86701809 -2.727
## Affluence 0.00269863 0.00066131 303.96272198 4.081
## Singletons.in.Tract 0.00074646 0.00061539 299.72023624 1.213
## Seniors.in.Tract 0.00051715 0.00077772 303.87838172 0.665
## African.Americans.in.Tract 0.00166186 0.00075214 306.25647171 2.210
## Noncitizens.in.Tract 0.00156578 0.00060980 276.48715410 2.568
## High.BP -0.00001273 0.00013652 301.28467440 -0.093
## Binge.Drinking 0.00036919 0.00014479 166.35074764 2.550
## Cancer -0.00040189 0.00080281 271.41128415 -0.501
## Asthma 0.00058005 0.00048061 146.97846941 1.207
## Heart.Disease 0.00292860 0.00103331 220.12588867 2.834
## COPD -0.00113513 0.00078250 213.82390951 -1.451
## Smoking -0.00023703 0.00018039 259.10535602 -1.314
## Diabetes -0.00106169 0.00038619 274.55848459 -2.749
## No.Physical.Activity 0.00026626 0.00015541 244.97404079 1.713
## Obesity 0.00021053 0.00012504 307.72297475 1.684
## Poor.Sleeping.Habits 0.00025096 0.00012068 299.06971366 2.080
## Poor.Mental.Health -0.00009963 0.00040933 107.04048937 -0.243
## Pr(>|t|)
## (Intercept) 0.00696 **
## Affluence 0.0000574 ***
## Singletons.in.Tract 0.22609
## Seniors.in.Tract 0.50658
## African.Americans.in.Tract 0.02788 *
## Noncitizens.in.Tract 0.01076 *
## High.BP 0.92574
## Binge.Drinking 0.01168 *
## Cancer 0.61706
## Asthma 0.22941
## Heart.Disease 0.00502 **
## COPD 0.14835
## Smoking 0.19002
## Diabetes 0.00637 **
## No.Physical.Activity 0.08793 .
## Obesity 0.09326 .
## Poor.Sleeping.Habits 0.03842 *
## Poor.Mental.Health 0.80815
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence -0.059
## Sngltns.n.T -0.052 0.041
## Snrs.n.Trct 0.387 0.293 0.073
## Afrcn.Am..T 0.239 0.077 -0.404 0.203
## Nnctzns.n.T -0.072 0.153 0.124 0.058 -0.193
## High.BP -0.093 0.158 0.098 0.008 -0.229 0.321
## Bing.Drnkng -0.495 -0.033 -0.203 -0.065 0.041 -0.076 0.147
## Cancer -0.493 -0.094 0.231 -0.168 -0.075 -0.063 -0.331 -0.015
## Asthma -0.273 -0.092 -0.262 -0.124 -0.018 0.214 0.046 0.013 -0.155
## Heart.Dises -0.061 0.082 -0.303 -0.133 0.213 -0.057 0.005 0.033 -0.603
## COPD 0.479 0.003 0.132 0.169 -0.009 0.156 0.054 0.056 -0.209
## Smoking -0.039 0.104 -0.119 -0.139 -0.104 0.158 -0.082 -0.327 0.154
## Diabetes 0.036 -0.303 -0.076 -0.131 -0.231 -0.247 -0.449 0.074 0.372
## N.Physcl.Ac -0.118 0.036 0.103 0.079 0.059 -0.275 0.004 0.131 0.332
## Obesity -0.067 0.381 0.398 0.199 0.132 0.190 -0.103 -0.143 0.117
## Pr.Slpng.Hb -0.383 -0.346 0.161 -0.323 -0.319 -0.047 -0.157 0.087 0.027
## Pr.Mntl.Hlt -0.352 0.185 -0.010 0.030 0.055 -0.162 0.032 0.128 0.415
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.334
## COPD -0.318 -0.495
## Smoking 0.144 0.086 -0.474
## Diabetes -0.105 -0.438 -0.001 0.275
## N.Physcl.Ac -0.019 -0.357 0.088 -0.274 -0.168
## Obesity -0.121 -0.019 0.090 -0.219 -0.374 -0.043
## Pr.Slpng.Hb 0.001 0.238 -0.090 -0.173 -0.062 -0.151 -0.115
## Pr.Mntl.Hlt -0.440 -0.063 -0.391 -0.031 0.069 -0.092 0.022 -0.077Testing Rate
testing.data.state <- compiled.stats[[length(daily_filenames)]][, c("Province_State", "Testing_Rate")]
testing.data.state <- testing.data.state[!is.na(testing.data.state$Testing_Rate),]
testing.data.state <- testing.data.state[order(testing.data.state$Testing_Rate),]
col.state <- rep("pink", nrow(testing.data.state))
avg.test.rate <- mean(testing.data.state$Testing_Rate, na.rm = T)
col.state[testing.data.state$Testing_Rate < avg.test.rate] <- "grey"
col.state[testing.data.state$Province_State == "Oklahoma"] <- "lightblue"
par(mar = c(5,6,4,2))
barplot(testing.data.state$Testing_Rate, names.arg = testing.data.state$Province_State, horiz = T, main = "Testing Rate by State", las = 2, cex.axis = 1, cex.names = 0.5, col = col.state, border = F, xlab = "Total number of people tested per 100,000 persons.")
abline(v = avg.test.rate, col = "red")
text(x = avg.test.rate + 10, y = 1, labels = "Average Testing Rate", adj = c(0, 0.5), col = "red")
Pink highlights the last 14 days.
day.first.case <- min(which(US.total$cases.total > 100))
n.days <- nrow(US.total)
twoweek.col <- c(rep("grey", n.days-day.first.case-13), rep("pink", 14))
par(mar = c(5,5,4,2))
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$rise.cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Cases of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$rise.deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Deaths of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)